Add a Gating task and draw your gates as you would for manual analysis.
Pick the file that best represents how plots look across your dataset. Viewing several plots side by side in the Gating task helps you compare candidates.
Choose the gates to adapt and the files to apply them to. AdaptiGate fits each gate to the data in every selected file.
Adapted gates switch to per-file mode, so you can check and edit gates if needed.
Automated gating uses an algorithm to place or adjust gates that identify cell populations in flow cytometry data, instead of drawing and adjusting every gate by hand. It addresses sample-to-sample variation and consistently applies a single gating strategy across large datasets. In OMIQ, automated gating is provided by AdaptiGate.
In manual gating, an analyst manually sets boundaries and adjusts them file by file as populations shift. With AdaptiGate, you define gates on a single template file, and the model automatically fits those gates to each selected file in your dataset. Adapted gates convert to a per-file mode, allowing you to review, fine-tune, or edit any gate by hand if needed.
AdaptiGate's machine-learning model was trained using expert-curated template data alongside crowdsourced flow cytometry annotations generated through Project Discovery, a citizen science project within EVE Online. Over six years, Project Discovery players analyzed more than 52,000 bivariate cell plots from 37 studies, generating more than 31,000 quality-controlled training plots. The underlying methodology is described in a 2025 bioRxiv preprint (Montante et al., doi:10.1101/2025.10.07.679685).
Yes. AdaptiGate requires only one representative template file and can be applied to any number of selected samples, making it equally effective for small pilot experiments and large multi-plate cohorts. AdaptiGate runs natively within the standard Gating task in OMIQ.
FlowJo's Autogate generates a polygon based on event density on a single bivariate plot (similar to its contour plot algorithm), while Magnetic Gates shift existing boundaries toward local maximum event densities. AdaptiGate takes a data-set wide approach: you set your gating strategy on a template file, and machine learning adapts those gates across all selected files while preserving your full gating hierarchy and logic.
AdaptiGate starts with gates defined by you on a template file and adapts those boundaries to individual files. Clustering algorithms such as FlowSOM instead group cells based on marker expression without requiring predefined gates or known populations. Clustering is therefore commonly used for exploratory analysis, while AdaptiGate automates an existing gating strategy. OMIQ supports both approaches, so you can use AdaptiGate and FlowSOM within the same workflow.
Yes, for routine analysis. AdaptiGate replaces the need to manually draw, shift, and adjust gates across every sample in a dataset. However, it keeps the analyst in full control: you define the initial template strategy and can review or override any gate output, ensuring complete oversight and compliance without doing the heavy lifting by hand.
AdaptiGate is included in OMIQ Essentials, Professional and Enterprise plans, as well as the free trial. Custom autogating services are available separately for Enterprise customers.
